Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the importance or significance of something within a specific context

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing the importance or integral role of elements in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     dolphins
    -0.70
     blond
    -0.68
     Predators
    -0.68
     ceilings
    -0.67
     spiders
    -0.66
     jets
    -0.65
     Bin
    -0.64
     lions
    -0.64
     mete
    -0.63
     faint
    -0.63
    POSITIVE LOGITS
    ainer
    0.75
    NER
    0.72
    PsyNetMessage
    0.71
    esan
    0.71
    Marginal
    0.70
    breaker
    0.69
    ICLE
    0.69
    stone
    0.69
    ãĥ¼ãĥĨ
    0.68
    UID
    0.67
    Act Density 0.085%

    No Known Activations